Neighborhood rough set based multi‐label feature selection with label correlation

Abstract

Summary Neighborhood rough set (NRS) is considered as an effective tool for feature selection and has been widely used in processing high‐dimensional data. However, most of the existing methods are difficult to deal with multi‐label data and are lack of considering label correlation (LC), which is an important issue in multi‐label learning. Therefore, in this article, we introduce a new NRS model with considering LC. First, we explore LC by calculating the similarity relation between labels and divide the related labels into several label subsets. Then, a new neighborhood relation is proposed, which can solve the problem of neighborhood granularity selection by using the nearest neighbor information distribution of instances under the related labels. On this basis, the NRS model is reconstructed by embedding LC information, and the related properties of the model are discussed. Moreover, we design a new feature significance function to evaluate the quality of features, which can well capture the specific relationship between features and labels. Finally, a greedy forward feature selection algorithm is designed. Extensive experiments which are conducted on different types of datasets verify the effectiveness of the proposed algorithm.

BMFS: Bidirectional weighted approach for multi-label feature selection algorithm

“…17 By considering the label correlation, Wu et al divided the relevant labels into multiple label subsets, and then introduced the label correlation into the neighborhood rough set model. 18 However, multi-label neighborhood rough sets use neighborhood granules to describe decision equivalence classes approximately, which cannot describe the uncertainty of instances under fuzzy background.…”